Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/romshark/datapages/agents-mdgit clone --depth 1 https://github.com/romshark/datapagesWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.04797 | $0.04797 |
| Opus 5 | $0.02398 | $0.02398 |
| Sonnet 5 | $0.00959 | $0.00959 |
| Haiku 4.5 | $0.00480 | $0.00480 |
Grade A, and why
datapages AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Style
- Follow standard Go conventions (Effective Go).
- Comment as described in code comments.
- Use
requirefrom testify for test assertions, useassertonly where it makes sense. - Use table-driven map-based (to ensure random input ordering) tests where applicable with concise name tests as map keys.
Commands
- Lint:
mage lint - Format:
mage fmt - Tidy all Go modules:
mage modTidy - Test (runs lint first):
mage test - Coverage of the generator and of the code it generates:
mage coverage - Build CLI and examples:
mage build - Generate templ files:
mage genTempl - Generate datapages code:
mage genDatapages - Generate all (templ + datapages + docs):
mage gen - Check that all generated code is current:
mage checkGen - Run go fix on all modules:
mage goFix - Run everything:
mage all
Project Structure
Internal, used by the CLI and build tooling:
internal/parser/- parses the application model from a Go source package.model/- the data model.validate/- naming convention validation.errsuggest/- "did you mean" suggestions for parser errors.internal/- method kinds, parameter validation, struct inspection, templ linting, type predicates, URL paths.testdata/- one self-contained module per fixture. Prefixerr_for expected-error cases.
internal/generator/- code generation from the parsed model.internal/generator/README.mdexplains its tests.internal/acceptance/- one module per case: the application, its committed generated code and tests asserting behaviour over HTTP.internal/acceptance/README.mdexplains how they run and how to record a defect the framework has not fixed yet.internal/gotypes/- go/types predicates and renderings that know nothing about Datapages. Shared by the parser and the generator.internal/routepattern/- net/http ServeMux route pattern parsing.internal/structtag/- thepath,query,jsonandreflectsignaltags.internal/subject/- broker subject rules: the token rule and which subjects an event claims.internal/serverscan/- finds the app package and the target package from thedatapages.NewServercalls. AST only, so it reads amain.gonaming a package the first run has not written yet.internal/templatingbench/- the templating benchmarksFAQ.mdquotes.internal/cmd/- CLI command implementations,package cmd.internal/tools/render-pages/- rendersdocs/index.html.internal/docs-src/- templ source and CSS for the docs page.docs/- generated GitHub Pages output.magefiles/- build targets.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 415 lines · 4,797 tokens per session scan A c8cd89ca51f5
datapages AGENTS.md is an instructions file published in the GitHub repository romshark/datapages (87 stars, last pushed 3d ago), licensed MIT. It adds 4,797 tokens to every session, about $0.0240 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
jesse AGENTS.md
Instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
AgentEval copilot-instructions.md
Instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.
AgentEval tracing.instructions.md
Guidelines for implementing trace recording and replay.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.